requests-BeautifulSoup爬取美女贴吧图片

xx才是第一生产力

爬取页面http://tieba.baidu.com/p/2166231880

1.getHtml(url)根据页面链接获取页面内容，值得值得注意的是这里使用了see_lz=1的参数获得只看楼主的页面，防止其他图片的干扰

2.getImgUrl(ulist,html)使用了bs4库的find_all()方法得到所有图片的链接并存储到ulist中

3.downloadImg(ulist)方法根据链接下载图片，运行程序后图片存储在d:/pic/目录中

#爬取美女图片
import requests
from bs4 import BeautifulSoup
import bs4
import os
def getHtml(url):
	kv={'see_lz':1}#设置只看楼主参数
	try:
		r = requests.get(url,params=kv)
		r.raise_for_status()
		r.encoding = r.apparent_encoding#因为爬取的是图片,其实没必要改变编码
		return r.text
	except:
		return ""
'''
方法功能:获取页面所有的图片链接，并储存在ulist中
'''
def getImgUrl(ulist,html):
	soup = BeautifulSoup(html,'html.parser')
	ccs = soup('cc')
	for cc in ccs:
		for img in cc('img'):
			ulist.append(img.attrs['src'])
	pass

def downloadImg(ulist):
	root = "D://pics//"
	try:
		if not os.path.exists(root):
			os.mkdir(root)
		for url in ulist:
			path = root+url.split('/')[-1]
			r = requests.get(url)
			if not os.path.exists(path):
				with open(path,'wb') as f:
					f.write(r.content)
					f.close()
	except:
		pass

def main():
	ulist=[]
	url='http://tieba.baidu.com/p/2166231880'
	html = getHtml(url)
	getImgUrl(ulist,html)	
	downloadImg(ulist)
main()